NOTE: This package is in development. Function design, names and arguments may change.
psymisc is an R package that provides some useful high-level and helper functions for psychologists that make everyday data analysis a little bit easier.
*_apa()
: A set of functions for formatting statistical output according to APA guidelines, ready to copy-and-paste into manuscripts (supports Text, Markdown, RMarkdown, HTML, LaTeX, docx1 and R's plotmath syntax). Currently available methods areanova_apa()
2,chisq_apa()
,cor_apa()
andt_apa()
. These functions were heavily influenced by the*_out()
functions in the schoRsch package.apa()
: A wrapper around the*_apa()
-functions for use in inline code in RMarkdown documents.cohens_d()
/cohens_d_()
: Calculate Cohen's d effect size (from raw data, t-test or statistical parameters). Also supports Hedge's g* and Glass's Δ.ci()
: Confidence interval around the mean.cor_table()
: Create a correlation matrix similar tocor
but with significance asterisks.ds()
: An alternative toaggregate()
for summary statistics. It wrapsdplyr::group_by()
anddplyr::summarise()
into a convenient formula interface.fplot()
: Convenient plotting of means and standard errors or boxplots of factorial data.mean_cor()
: Calculate the mean of several correlations using Fisher-Z-transformation.moe()
: Margin of error, half the width of the confidence interval around the mean.plotsig()
: A convenience function for displaying significance in ggplot2 plots.recode()
: Recode variables based on multiple rules.routlier()
: Remove or flag outliers.se()
: Standard error of the mean, SE = SD(x) / sqrt(n)stats_table()
: Compare group characteristics (means and standard deviations plus significance tests). Outputs to either the console, HTML (which can then be copy-and-pasted directly into Word) or LaTeX.t_test()
: A wrapper fort.test()
that includes the original data in its return list (in order to calculate the effect size incohens_d()
andt_apa()
directly from the data).
1 pandoc is required for docx output and needs to be installed manually when not using RStudio (which ships pandoc).
2 Supports input from ezANOVA()
from the ez package and aov_ez()
/ aov_car()
/ aov_4()
from the afex package.
The development version can be installed using:
install.packages("devtools")
devtools::install_github("dgromer/psymisc")